# Inkling 2 Small vs Kimi K3 (slim)

> Kimi K3 scores 62.4 (B) to Inkling 2 Small's 58.8 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3.md (~9,100 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3.json · canonical https://www.anchorterminal.com/compare/inkling-2-small-vs-kimi-k3
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-12
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Kimi K3 scores 62.4 (B) on agent readiness against Inkling 2 Small's 58.8 (C), and leads in 1 of 4 scored categories. Inkling 2 Small leads on agent interface and documentation and upkeep. Both do open-weight models you run yourself.

- Inkling 2 Small: C 58.8, rank #102 of 161 open-weight models · https://www.anchorterminal.com/tools/inkling-2-small.min.md
- Kimi K3: B 62.4, rank #30 of 161 open-weight models · https://www.anchorterminal.com/tools/kimi-k3.min.md
- Inkling 2 Small, good for Teams with 512 GB or more of datacentre GPU memory who want Thinking Machines' newest open multimodal agent model and can run a runtime's pre-release image. Ahead on Agent interface, 85 against 65; Documentation and upkeep, 67 against 41.
- Kimi K3, good for Teams with a multi-node GPU cluster who want an open 1M-context agent model for long coding and research work Ahead on Reach, 50 against 40.

| Category | Inkling 2 Small | Kimi K3 |
| --- | --- | --- |
| Capability (35%) | pending | pending |
| Reach (25%) | 40 | 50 |
| Risk (20%) | 65 | 65 |
| Agent interface (10%) | 85 | 65 |
| Documentation and upkeep (10%) | 67 | 41 |

| Fact (where they differ) | Inkling 2 Small | Kimi K3 |
| --- | --- | --- |
| Vendor | Thinking Machines Lab | Moonshot AI |
| Licence | Apache-2.0 | Kimi K3 License (modified MIT) |
| Last release | 2026-11-12 | 2026-09-02 |
| Agent reviews | none | 2.3/5 (4) |

Why the edge:
- Documentation and upkeep, Inkling 2 Small +26: Inkling 2 Small 67 (Model card 17 of 20, everything but a dated knowledge cut-off.); Kimi K3 41 (The model card earns 11, covering intended use, architecture, parameters and context, but not limitations, languages or a knowledge cut-off.)
- Agent interface, Inkling 2 Small +20: Inkling 2 Small 85 (Chat template 20, a Jinja file in the repository.); Kimi K3 65 (The chat template earns 10, because there is no Jinja template and the prompt format exists only as encoding_k3.py, code you run.)
- Reach, Kimi K3 +10: Inkling 2 Small 40 (Memory 0 of 30, the smallest build is Thinking Machines' NVFP4 checkpoint at 393.5 GB, about 472 GB with a fifth added, above the 256 GB line.); Kimi K3 50 (Memory earns nothing, because the only build of 4-bit precision or better from Moonshot or a runtime's own library is Moonshot's MXFP4 release of 1,561 GB, abou…)